Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ()
↵
↵
    -0.06
     SUB
    -0.06
     AMC
    -0.06
    teams
    -0.06
    _FD
    -0.06
    _pdf
    -0.06
     आई
    -0.06
     Ain
    -0.05
    DOC
    -0.05
     đặt
    -0.05
    POSITIVE LOGITS
     governo
    0.07
     feudal
    0.07
    -runtime
    0.07
     Syndrome
    0.07
    oreal
    0.07
    贵
    0.06
     franç
    0.06
    民主
    0.06
    siniz
    0.06
    貴
    0.06
    Act Density 0.148%

    No Known Activations